Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LerianStudio/ring --skill researching-featuresgit clone --depth 1 https://github.com/LerianStudio/ringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lerianstudio/ring/researching-features)<a href="https://agentmods.dev/skills/lerianstudio/ring/researching-features"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/researching-features.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00106 | $0.00982 |
| Opus 5 | $0.00053 | $0.00491 |
| Sonnet 5 | $0.00021 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
ring:researching-features scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Dev Research Skill (Gate 0)
When to use
- Before any pre-dev workflow (Gate 0 of both tracks)
- When planning new features or modifications
- Invoked by /ring:planning-large-features and /ring:planning-small-features
Skip when
- Trivial changes that don't need planning
- Research already completed (research.md exists and is recent)
Sequence
Runs before: ring:writing-prds (Gate 1)
Related
Complementary: ring:writing-prds, ring:writing-trds
Gathers deep technical/product research BEFORE writing planning documents, ensuring PRDs and TRDs are grounded in codebase reality, prior art, and authoritative technical sources.
Scope is technical/product only. Research covers: the product/feature itself (what it is, how comparable products solve it), technical approach, third-party integrations, prior art, and existing codebase patterns. ZERO business content — no market analysis, no personas, no user research, no go-to-market.
Step 1: Determine Research Mode
| Mode | When | Agent Priority |
|---|---|---|
| greenfield | New capability (no existing patterns) | Web research primary |
| modification | Extending existing functionality | Codebase research primary |
| integration | Connecting external systems | All agents equally weighted |
If unclear, ask: "Is this (1) Greenfield, (2) Modification, or (3) Integration?"
Step 2: Dispatch 3 Agents in Parallel
Single message, 3 Task calls:
| Agent | Focus | Mode Priority |
|---|---|---|
ring:repo-researcher |
Codebase patterns for [feature]; search docs/solutions/ knowledge base; return file:line refs | PRIMARY in modification |
ring:web-researcher |
Technical approach, prior art, and best practices for [feature]; use firecrawl (search/scrape/crawl) + exa; return URLs | PRIMARY in greenfield |
ring:docs-researcher |
Tech stack docs for [feature]; detect versions from manifests; firecrawl scrape/crawl of official docs + exa search; return version constraints | PRIMARY in integration |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 110 lines · 106 tokens per session scan A 7e06f4a9373e
ring:researching-features is a skill published in the GitHub repository LerianStudio/ring (211 stars, last pushed 19d ago), licensed Apache-2.0. It adds 106 tokens to every session and 982 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
calibration
Internal dynos-work skill. Agent calibration — generates project-specific agents, benchmarks them, promotes/demotes based on performance, and manages auditor mode transitions. Runs only when the user explicitly types /dynos-work:calibration; never auto-triggered from conversation.
maintain
Internal dynos-work skill. Autonomous maintenance worker. Scans the repo for technical debt, security anti-patterns, and architectural drift; on a finding it creates a repair branch, implements the fix, verifies with audits/tests, and opens a Pull Request. Runs only when the user explicitly types /dynos-work:maintain…
ds-brief
Data-backed brief — research, source, double-verify, and render a visually rich single-file HTML report. Use when the user wants a sourced, fact-checked brief or report on a topic.
ds-ship
Ship orchestrator — classify the project, pick a mode (improve/release/launch/maintain), delegate only the skills the project's signals justify, consolidate findings, produce an audit report. Use for an end-to-end audit or ship pipeline across multiple skills.
trajectory
Internal dynos-work skill. Sequence memory manager. Stores compact task traces and retrieves similar prior tasks to inform discovery and design review. Runs only when the user explicitly types /dynos-work:trajectory; never auto-triggered from conversation.
ds-deploy
Deployment and infrastructure — containerization, deployment, monitoring, incident response. Use when deploying an app, setting up containers/monitoring, or planning incident response.